Giters

Rostlab / EAT

Embedding-based annotation transfer (EAT) uses Euclidean distance between vector representations (embeddings) of proteins to transfer annotations from a set of labeled lookup protein embeddings to query protein embedding.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

error: no module named 'transformers'

shoumo2021 opened this issue · comments

commented

Following installation as described, eat.py is no longer working - with error message:
shoumo@Shoumos-MacBook-Pro-2 EAT % python eat.py --lookup data/example_data_subcell/deeploc_lookup.fasta --queries data/example_data_subcell/la_query_setHARD.fasta --output eat_results/

Traceback (most recent call last):
File "/Users/shoumo/EAT/eat.py", line 515, in
main()
File "/Users/shoumo/EAT/eat.py", line 496, in main
eater = EAT(lookup_p, query_p, output_d,
File "/Users/shoumo/EAT/eat.py", line 216, in init
self.lookup_ids, self.lookup_embs = self.read_inputs(lookup_p)
File "/Users/shoumo/EAT/eat.py", line 262, in read_inputs
self.Embedder = Embedder()
File "/Users/shoumo/EAT/eat.py", line 129, in init
self.embedder, self.tokenizer = self.get_prott5()
File "/Users/shoumo/EAT/eat.py", line 135, in get_prott5
from transformers import T5EncoderModel, T5Tokenizer
ModuleNotFoundError: No module named 'transformers'

commented

Yeah, sorry I've messed up the requirements with one of my last edits.
I've re-added the transformers library.